An Integrated Strategy for Autonomous Exploration of Spatial Processes in Unknown Environments

Abstract

<jats:p>Exploration of spatial processes, such as radioactivity or temperature is a fundamental task in many robotic applications. In the literature, robotic exploration is mainly carried out for applications where the environment is a priori known. However, for most real life applications this assumption often does not hold, specifically for disaster scenarios. In this paper, we propose a novel integrated strategy that allows a robot to explore a spatial process of interest in an unknown environment. To this end, we build upon two major blocks. First, we propose the use of GP to model the spatial process of interest, and process entropy to drive the exploration. Second, we employ registration algorithms for robot mapping and localization, and frontier-based exploration to explore the environment. However, map and process exploration can be conflicting goals. Our integrated strategy fuses the two aforementioned blocks through a trade-off between process and map exploration. We carry out extensive evaluations of our algorithm in simulated environments with respect to different baselines and environment setups using simulated GP data as a process at hand. Additionally, we perform experimental verification with a mobile holonomic robot exploring a simulated process in an unknown labyrinth environment. Demonstrated results show that our integrated strategy outperforms both frontier-based and GP entropy-driven exploration strategies.</jats:p>

Autonomous robotic exploration with simultaneous environment and traversability models learning

“… Karolj et al (2020) computed a path to the closest spatial frontier that visits all local sampling locations for a magnetism model by solving the Traveling Salesman Problem (TSP) over the respective goal locations. In localization in mapping, Ossenkopf et al (2019) note that occupancy information gained at an unknown location holds little value and thus weight the occupancy gains by a pose uncertainty ( Vallvé and Andrade-Cetto, 2015 ).…”

“…In addition, we aim to build a modular system that supports the learning of models that range from the spatial map and cost predictors used in this study to temperature and pollution models. Hence, instead of creating a combined information gain utility function using the Rényi entropy, which is suitable for the combination of a map and robot’s localization model used by Carrillo et al (2018) , we elect to use a policy that combines the spatial exploration and cost learning goals (and goals reported by any additional model), similarly to the approach proposed by Karolj et al (2020) .…”

“…20) and the histogram descriptor, respectively. Therefore, similar to Karolj et al (2020) , the kernel hyperparameters l and and GP’s have fixed values that we consider to be dependent on the system parameters.…”

Adaptive Visual Information Gathering for Autonomous Exploration of Underwater Environments

“…Information Gathering (IG) algorithms guide such exploration using an information metric which represents the informativeness of the environment variable under study in particular locations, and this metric is used to drive the data recording process towards the more informative spots whilst minimizing a cost, such as the number of measurements, the navigation distance or the mission time. IG algorithms have been used for different types of exploration, for instance; (a) goal-based, where the objective is traveling from an initial location to a goal location with a given cost budget [8], [9], [10], (b) front-based, for traversing a given threshold area [11], [12], (c) frontier-based, usually for indoor environment mapping [13], [14], [15], [16], (d) multimodal, using different data sources [17], [18], (e) multirobot, using multiple robots [19], [20], [21], (f) hotspot-based, to find environmental variable hotspots [22], [23], and (g) coveragebased, for environmental variables dense estimation [24], [25], which is, in fact, the focus of this work.…”

“…The literature is scarce in terms of adaptive replanning methods. Whilst the usual [31], [14] is to provide a linear execution pipeline where the vehicle is stopped for mapping and planning, some authors propose to perform the process of environmental modeling in parallel to the planning process [43], and even start planning in a further location of the current mission path to avoid stopping the vehicle [25]. Furthermore, most relevant strategies, either sampling-based [31] or evolutionary-based [25] do not transfer planning knowledge between consecutive planning iterations.…”